Convergence problem PreviousNext
Mplus Discussion > Structural Equation Modeling >
Message/Author
 Anonymous posted on Tuesday, January 14, 2003 - 9:21 am
Hello,

I have a convergence problem on residual covariance about two variables in SEM.

(1)I tried to add the number of iteration to 10000, but it still does not work.

(2) I tried different starting values, e.g., 0.05,0.5, 1, 10, it does not work, either.

In output, it says:

NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED.


ZERO CELL PROBLEM: IR, J & K = 1 6 1
.
.
.


How to solve that problem?

Thanks

Daniel
 Linda K. Muthen posted on Tuesday, January 14, 2003 - 9:28 am
You should send your output and data to support@statmodel.com.
 Anonymous posted on Thursday, September 30, 2004 - 5:51 am
I do have a question concerning the starting values: Which starting values should be used? Is it possible just to try out different starting values like 0.5, 1.0 or -1.0 and see which starting values generate the best cfi, tli, etc? Could you explain what changes when I use different starting values? Please excuse the very trivial question, but I'm new to MPlus.
 Linda K. Muthen posted on Thursday, September 30, 2004 - 7:58 am
In most cases starting values are not needed. Different starting values should not yield different solutions unless a local solution is reached.
 Reetu posted on Wednesday, February 01, 2006 - 12:31 pm
Hi,
I'm having a convergence problem. My current SEM isn't converging. I've tried reducing the convergence criterion, increasing the number of iterations to 10000 and don't know what to do now.

The error that's coming up says:

NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED.


Any suggestions?
 Linda K. Muthen posted on Wednesday, February 01, 2006 - 1:06 pm
The user's guide has suggestions. Look under convergence problems. If that doesn't help, send your input, data, output, and license number to support@statmodel.com.
 Reetu posted on Thursday, February 02, 2006 - 2:18 pm
What is the default starting value that MPlus uses?
 Linda K. Muthen posted on Thursday, February 02, 2006 - 2:54 pm
It depends on the parameter and the model. See the user's guide under defaults. You can see the starting values used by asking for TECH1 in the OUTPUT command.
 Rina posted on Saturday, June 23, 2007 - 1:29 am
Hi,
I am having a convergence problem.

I am doing a path analysis. The IDVs are 3 observed continuous variables. The DVs are 3 latent continous variables, which are
factor 1 by a b c;
factor 2 by d e f;

The output told me that the data was not converged and that the problem was found in the covariance of the two latent Vs. I found that in the variance covariance matrix, the pattern of covariance looked like this:

Cov (a,d)=cov (a,e)=cov (a,f)
Cov (b,d)=cov (b,e)=cov (b,f)
ˇ­
Cov (f,a)=cov (f,b)=cov (f,c).

I am wondering if this is normal? How should I solve this problem and get the model run?
Thank you!
 Linda K. Muthen posted on Saturday, June 23, 2007 - 5:50 am
Please send your input, data, output, and license number to support@statmodel.com.
 Jeannine Tamez posted on Thursday, July 26, 2007 - 11:12 am
Hi,

I am also getting a "NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED." I have increased the # of iterations to 10000 and am unsure as to determine which starting values to assign to which variables. Please advise.

Also, should I be concerned that the estimates for f2 are substantially higher than the estimates for f1?



MODEL RESULTS

Estimates

F1 BY
A1 0.072
A3 0.043
A16 0.055


F2 BY
A5 1.000
A6 -737.174
A10 217.103
A13 -9.586
A15 780.447
A17 2279.995


Thank you.
 Linda K. Muthen posted on Thursday, July 26, 2007 - 11:58 am
Please send your input, data, output, and license number to support@statmodel.com.
 Jungeun Lee posted on Monday, December 29, 2008 - 2:11 pm
Hello,

I am estimating a CFA and am getting '
NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED.'warning. I increased # of iterations=10000 but still got the same message... Any advice will be deeply appreciated. Thanks!
 Linda K. Muthen posted on Monday, December 29, 2008 - 2:15 pm
Please send your input, data, output, and license number to support@statmodel.com.
 Katherine Yu posted on Wednesday, May 11, 2011 - 11:45 am
I also met this problem. I got the message 'NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED' even I increased the number of iteration to 10000. I knew the range of my sample variance values is too large, but I don't know how to revise it. Thank you.
 Linda K. Muthen posted on Wednesday, May 11, 2011 - 3:34 pm
You can use the DEFINE command to rescale continuous variable by dividing them by a constant. You should use a constant that brings the variances between one and ten.
 Kathrin Gasser posted on Monday, July 25, 2011 - 1:50 pm
I have a sample of performance measures and I use "age" as the time variable. When I specify estimator=ML, the model is estimable from 20-38. If I use estimator=MLR, the model only converges until 20-33. The covariance coverages decreases if I increase the number of "waves" (age) in the analysis due to drop-outs. What are the minimum criteria for MLR (as opposed to ML)?
 Linda K. Muthen posted on Monday, July 25, 2011 - 2:22 pm
ML and MLR should behave the same. For further comments, send the relevant outputs and your license number to support@statmodel.com.
 Anna Potocki posted on Thursday, September 22, 2011 - 2:24 am
Hi,
I am also getting this message "NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED.FACTOR SCORES WILL NOT BE COMPUTED DUE TO NONCONVERGENCE OR NONIDENTIFIED MODEL." I am wondering if there is any possibility to avoid this message and to run the model or if the problem relies on my model itself.. I'm sorry, I'm really new in Mplus. Could you help me?
Thank you!
 Linda K. Muthen posted on Thursday, September 22, 2011 - 6:27 am
This is a function of your model and data. Please send the output and your license number to support@statmodel.com.
 Cory Dennis posted on Thursday, November 17, 2011 - 10:19 am
RE: "You can use the DEFINE command to rescale continuous variable by dividing them by a constant. You should use a constant that brings the variances between one and ten."

Does this apply to ordered-categorical as well? In other words if variance for categorical and continuous variables exceeds 10:1, does the same apply?
 Linda K. Muthen posted on Thursday, November 17, 2011 - 10:36 am
No, this applies to continuous variables. You should not rescale categorical variables.
 Cory Dennis posted on Thursday, November 17, 2011 - 11:04 am
Thanks.

So I get a "NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED" message when running my model. The problem appears to be between one of the LV with continuous outcomes and one of the LV with ordinal(using ULSMV). When rescaling the continuous indicators my model converges.

On the other hand, I am able to get results with multiple imputed data sets using the original scale (with a warning on two of data sets regarding theta). Should I rescale the continuous variables?
 Linda K. Muthen posted on Thursday, November 17, 2011 - 11:33 am
I think it is always a good idea to keep variances of continuous variables between one and ten particularly when you have a combination of continuous and categorical variables.
 Jan Eichhorn posted on Tuesday, December 06, 2011 - 1:08 am
Hello,
I am running a model with 4 dimensions of integration and cannot seem to get it to converge. I have latent-observed interactions in the model, so I am using Type=Random and Integration=Montecarlo. Following the advice in the handbook I increased integration points to 1000 and MIterations to 2500 but still get the error below. Does it make sense to increase iterations further or is there something else I should consider first? Thank you very much for your time.
Jan

THE MODEL ESTIMATION DID NOT TERMINATE NORMALLY DUE TO A NON-ZERO
DERIVATIVE OF THE OBSERVED-DATA LOGLIKELIHOOD.

THE MCONVERGENCE CRITERION OF THE EM ALGORITHM IS NOT FULFILLED.
CHECK YOUR STARTING VALUES OR INCREASE THE NUMBER OF MITERATIONS.
ESTIMATES CANNOT BE TRUSTED. THE LOGLIKELIHOOD DERIVATIVE
FOR PARAMETER 44 IS -0.22400526D-01.
 Linda K. Muthen posted on Tuesday, December 06, 2011 - 6:03 am
Please send the output and your license number to support@statmodel.com.
 Alcohol Study posted on Thursday, January 05, 2012 - 5:22 pm
Hello Drs. Muthen,


I am having an issue with a double mediation model causing a convergence problem. I get the following error when running the full model :

THE MODEL ESTIMATION TERMINATED NORMALLY

THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES COULD NOT BE
COMPUTED. THE MODEL MAY NOT BE IDENTIFIED. CHECK YOUR MODEL.
PROBLEM INVOLVING PARAMETER 23.

THE CONDITION NUMBER IS 0.659D-14.

When I run a simplified mediation model without one of the variables I get no error and decent fit, however, once I add that variable as an additional mediator, I get the error.

The scales used for the variables scales are not very different, the basic descriptives seem to be okay (all values within the response range, means, SDs and correlations all make sense) and the range of variance doesn’t appear to be too large. I also tried increasing the number of iterations to 10000 and the error persists. What do you think is the source of the problem and how would you advise to proceed?

Thank you,

Danit
 Linda K. Muthen posted on Friday, January 06, 2012 - 10:09 am
Please send your output and license number to support@statodel.com.
 Nidhi Kohli posted on Monday, February 06, 2012 - 4:00 pm
I am trying to fit a latent variable structural equation model. In the Mplus output I see an error message saying, "NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED." Can you please tell me what does this error message implies? How can I fix it? Thank you.
 Linda K. Muthen posted on Monday, February 06, 2012 - 4:19 pm
Something about your model and data cause the model not to converge. Please send the output and your license number to support@statmodel.com.
 Sarah Phillips posted on Friday, June 29, 2012 - 6:53 pm
Hello,

I am running a 3-level model using TWOLEVEL COMPLEX. Where students are my level 1, classrooms level 2, and teachers, level 3.

I am trying to confirm that the small number of students and students/classroom in some of my subgroups makes it impossible to do a multi-group analysis.

I am at the phase where I am trying to get my dependent and independent measurement models to converge on my subgroups separately (they work fine for the entire sample) and wanted to double check that the error messages I'm getting are consistent with having too few students or too few students/classroom.

My error messages include:


THE STANDARD ERRORS OF THE MODEL PARAMETER ESTIMATES COULD NOT BE
COMPUTED. THIS IS OFTEN DUE TO THE STARTING VALUES BUT MAY ALSO BE
AN INDICATION OF MODEL NONIDENTIFICATION. CHANGE YOUR MODEL AND/OR
STARTING VALUES. PROBLEM INVOLVING PARAMETER 15.

or

THE MODEL ESTIMATION DID NOT TERMINATE NORMALLY DUE TO AN ILL-CONDITIONED
FISHER INFORMATION MATRIX. CHANGE YOUR MODEL AND/OR STARTING VALUES.

I only have approximately 100 to 153 students in each of three groups of 17-25 classrooms. And, as you might expect, mean class size is pretty small.

Could these error messages be due to small sample sizes and/or the small number of students/classroom?

Thanks,

Sarah
 Bengt O. Muthen posted on Friday, June 29, 2012 - 8:39 pm
You should have more students per classroom and group than you have parameters specific to classrooms and group.

There might be another reason for your non-identification message - you might send to Support.
 Sarah Phillips posted on Monday, July 02, 2012 - 7:06 am
Thanks! -Sarah
 Cecily Na posted on Tuesday, July 17, 2012 - 10:04 am
Hello Professors,
I have done a CFA model with more than 10 factors. The fit is not great, but can be considered. I then added the structural part of the model, i.e. come causal links. The program complained about no convergence. I tried reducing variances of continuous variables to the range between 1 and 10, but that didn't work out. Can you help with it?
Thanks a lot!
 Linda K. Muthen posted on Tuesday, July 17, 2012 - 10:57 am
Please send the output and your license number to support@statmodel.com.
 lan jiang posted on Tuesday, January 08, 2013 - 12:38 pm
hi,
i have problem with convergence. i looked through this thread, and modified my data to having variance of continous variable between 1 and 10. and it didn't help.

also i tried to increase the maximum interation number, but i received a warning saying this analysis doesn't have this option.

in addition, i don't know how to decrease the convergence criteria to make the convergence.

here is partly my code:

your guidance is very much appreciated!

USEVARIABLES =O3 O4 PCT_O5 PCT_O6 O7 O8 O9 O10 O11 O12 O13 d1 d2 pct_d3 PCT_S1 PCT_S2 PCT_S3 PCT_S4 PCT_O1 PCT_O2 R2 R4 R5 R6 DTESTING ;
CATEGORICAL = O7 O8 O9 O10 O11 O12 O13 R2 R4 R5 R6 DTESTING;
ANALYSIS:
TYPE = general ;
ESTIMATOR=WLSMV; !FOR CATEGORICAL OTUCOME

MODEL:

ORG BY O3@1 O4 PCT_O5 PCT_O6 O7 O8 O9 O10 O11 O12 O13 d1;
SOCIO BY PCT_S1@1 PCT_S2 PCT_S3 PCT_S4;
PAY BY PCT_O1@1 PCT_O2;
REG BY R2@1 R4 R5 R6;

DIR BY d2@1 pct_d3;

PAY ON SOCIO;
ORG ON DIR;
SOCIO ON ORG;
DTESTING ON REG PAY;


OUTPUT:
standardized sampstat ;
 Bengt O. Muthen posted on Tuesday, January 08, 2013 - 2:42 pm
Please send your full output to Support@statmodel.com.
 lopisok posted on Monday, April 08, 2013 - 4:12 am
Dear reader,

I'm trying to create a full causal SEM model. It converges easily when I use ML as an estimator but when I use MLM as an estimator it doesn't converge (maximum number of iterations ...). Is there a reason why computation time increases so dramatically when using MLM as an estimator and why it suddenly doesn't converge? I tried increasing the number of iterations and I tried putting the variance of other items (who show large estimates) on 1 but it doesn't resolve the problem. I read in the manual some suggestions about convergence problems as changing the starting values but I'm not sure in what I'm supposed to change them.

Kind regards
 Linda K. Muthen posted on Monday, April 08, 2013 - 11:49 am
I would think the problem could be related to MLM using listwise deletion and ML using a FIML approach to missing data. This makes the data different for the two analyses.
 Cindy Masaro posted on Sunday, April 14, 2013 - 5:27 pm
Hi there,

I'm running a SEM with 10 latent variables and several single indicators and I can't seem to get it to converge despite changing the setting for the number of iterations and convergence. Any suggestions?

2 other questions:

1)If I want to make sure the endogenous variables are co-varying, do I have to specify each relationship in the syntax or is this accomplished by default in the program?

2) If I want to allow the error terms (psi) on the endogenous variables to co-vary, is this just a matter of specifying one variable WITH another?
 Linda K. Muthen posted on Monday, April 15, 2013 - 8:35 am
Please send your output and license number to support@statmodel.com.

1. The residuals of final dependent variables are correlated as the default.

2. Yes.
 Cindy Masaro posted on Monday, April 15, 2013 - 10:41 am
Hi Linda, I do not have any output as the program keeps working and never gets to the point where I get output.
 Linda K. Muthen posted on Monday, April 15, 2013 - 10:59 am
Then send the input, data, and your license number.
 lopisok posted on Monday, May 06, 2013 - 8:36 am
Dear Linda or Bengt or other readers,

I posted some time ago that I was trying to create a full causal SEM model. It converges easily when I use ML as an estimator but when I use MLM as an estimator it doesn't converge (maximum number of iterations ...). I asked if there was a reason why computation time increases so dramatically when using MLM as an estimator and why it doesn't converge?

You stated that this is probably related to: "MLM using listwise deletion and ML using a FIML approach to missing data. This makes the data different for the two analyses."

Is there a way to make the model converge using MLM? And is it normal that the computation time is so dramatically different? I tried increasing the number of iterations and I tried putting the variance of other items (ones that show large estimates) on 1 but it doesn't resolve the problem. I read in the manual some suggestions about convergence problems through changing the starting values but I'm not sure in what I'm supposed to change them.

Kind regards
 Linda K. Muthen posted on Monday, May 06, 2013 - 8:41 am
I would start with the measurement model to see if it fits the data. If you have convergence problems, free the first factor indicator of each factor and fix the factor variances to one, for example,

f BY y1* y2 y3;
f@1;

Once you get to measurement model fitting well and converging, add the rest of the model.
 lopisok posted on Tuesday, May 07, 2013 - 2:02 am
I freed the first factor indicator of one factor which created problem and fixed that factors variance to one. This worked. Thank you very much! Do you know any sources where I could find more background info why this suddenly works and before it would not converge? Why does fixing the variance of the factor to 1 and freeing the first indicator makes a difference in the computation?
 Linda K. Muthen posted on Tuesday, May 07, 2013 - 6:11 am
The first factor loading is probably being estimated at a value that is not close to the value of one that it was being fixed at. Freeing it allows you to see this. If you want to set the metric by fixing a factor loading to one, choose a factor indicator that is estimated close to one.
 Elina Dale posted on Wednesday, September 04, 2013 - 2:18 am
Dear Dr. Muthen,

As others who posted on this board, I got the message "Number of iterations exceeded."

In MPlus Guide, I see that convergence problems occur often when the range of sample variance exceeds 1 to 10, which happens with combinations of cont and categ outcomes. I believe this is my case.

I have tried, as advised in the Guide, to increase the number of iterations (STITERATIONS=100) but it doesn't improve the situation and I get the same message as before.

Could you please, advice on what can be done as the next step?

The Guide also advises to use the preliminary parameter estimates as starting values, but I do not know how to get them and use them. If you think that could help, could you please, help me with correct commands?

Thank you!
 Linda K. Muthen posted on Wednesday, September 04, 2013 - 6:29 am
Please send the output and your license number to support@statmodel.com.
 RuoShui posted on Tuesday, November 26, 2013 - 5:32 pm
Dear Dr. Muthen,

I am having a convergence problem--iteration exceeded. However, the exact same model that I ran using the same version of Mplus two weeks ago had no convergence problem. I do not understand who this happens. Would you please give me a hint?
I am sorry for the trivial question.

Thank you very much.
 Bengt O. Muthen posted on Tuesday, November 26, 2013 - 5:33 pm
Please send the two outputs to Support.
 Sarah Lowe posted on Saturday, March 15, 2014 - 10:07 am
Hi Drs. Muthen,

I am running a three-wave, three-variable cross-lagged model that runs fine when all of the variables are included as continuous. However, two of the variables are counts of different types of events (x 3 waves = 6 count indicators total), and our reviewers would like to model them as such. Each count variable is modeled as a single indicator onto a latent variable with mean set at 0.0 and variance set a 1.0.

I have tried the following to facilitate convergence:
- Using montecarlo integration (and altering the # of integration points)
- Increasing the # of iterations (to 10,000)
- Changing start values for parameters that have strange final starting values
- Changing start values for all parameters
- Various combination of the above

Most recent error message:

THE MODEL ESTIMATION DID NOT TERMINATE NORMALLY DUE TO AN ERROR IN THE
COMPUTATION. CHANGE YOUR MODEL AND/OR STARTING VALUES.

In our bivariate models [each including one type of event, and the symptom inventory], the pattern of results were consistent whether we modeled events as counts or continuous variables, so I was thinking of asking the editor if we could use continuous variables to facilitate convergence. However, I figured I would see if you have any any additional suggestions/insights before I do that.

As always, really appreciate your help,

Sarah
 Linda K. Muthen posted on Sunday, March 16, 2014 - 11:50 am
I would not put a factor behind the count variables. Use them as observed count variables. I believe this could be part of the problem.
 Sarah Lowe posted on Sunday, March 16, 2014 - 7:27 pm
Hi Linda,
Thanks for your response. The reason why we put factors behind the count variables was because we wanted to include within-wave covariances. When we ran the model with just counts, we got this error:

*** ERROR in MODEL command
Covariances for count variables with latent variables are not allowed on the
within level. Problem with the statement:
AVOID3 WITH COUNT3

Does that make sense?

All of the other models we have used with count variables modeled as latent variables thus far have worked... I think that there is something about including 2 times the number of count variables that is leading to convergence problems. Does this sound correct to you? Any advice on how to proceed?

Thanks again for your help,
Sarah
 Linda K. Muthen posted on Monday, March 17, 2014 - 9:37 am
Instead of putting a factor behind each count variable, you can specify the residual covariances as:

f BY c1@1 c2;
f@1; [f@0];

where the residual covariance is found in the factor loading for c2.

If you think the issue is too many count variables, try adding them to the count list one or a few at a time.
 Sarah Lowe posted on Monday, March 17, 2014 - 11:51 am
Thanks - I'll try that - appreciate your help
 Ina Sonego posted on Tuesday, May 06, 2014 - 6:05 am
Dear Dr. Muthen,

I am new to Mplus and have a convergence problem.

NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED.

I tried setting the iteration at 10000 and also fixing starting values. However, I am really not sure if I fixed the starting values right. Which ones should be fixed and how?

Thank you for you help
 Linda K. Muthen posted on Tuesday, May 06, 2014 - 10:22 am
Please send the output and your license number to support@statmodel.com.
 SY Khan posted on Friday, May 09, 2014 - 6:58 am
Hi Dr. Muthen,

I am estimating a moderated mediation path. All variables are continuous. I get the message

NO CONVERGENCE. NUMBER OF ITERATIONS EXCEEDED.

After increasing the number of iterations to ITERATIONS = 10000;

I get the following output:

Chi-sq=10.842
Df=2
p=0.0044
RMSEA=0.014
CFI=0.999
TLI=0.996

There are no negative variances/residual variances in the unstandardized/standardized estimates.All the regression co-efficients are in their expected direction and the interaction term is significant.

However,the variance for one variable (interaction term) is large (expressed as ****)in the output but its z-value=93.908*** in the unstandardized solution. And variance= 1 in the standardised solution.

Similarly in CONFIDENCE INTERVALS OF MODEL RESULTS: only the Lower .5% variance is large (expressed as ****). Rest of all confidence interval variances are available.

Under these circumstances is it ok to trust the model result as it gives me all the model fit and parameter estimates?

Thank you for your guidance and time.
 SY Khan posted on Friday, May 09, 2014 - 7:31 am
Hi again,

In continuation to my above question on increasing iteration due to non-convergence in the modearted mediation of continuous variables. I have tried to redifine the interaction term by dividing it with 100. and got the same model fit as I get when I increase the number of iterations.

But by redifining the interaction term which gave a large variance I now get the value for the variance as well.

Just wondering which way should I proceed and which is more correct?

Is it ok to re-difine the interaction term when it is of the most importance and significance in the model?

Thanks for your input in advance and sorry for posting simultaneously.
 Linda K. Muthen posted on Friday, May 09, 2014 - 8:50 am
We recommend keeping variances of continuous variables between one and ten. We recommend dividing the variable by a constant to bring the variances between one and ten.

Please do not exceed one window when you post.
Back to top
Add Your Message Here
Post:
Username: Posting Information:
This is a private posting area. Only registered users and moderators may post messages here.
Password:
Options: Enable HTML code in message
Automatically activate URLs in message
Action: